view release on metacpan or  search on metacpan

LibNeural.pm  view on Meta::CPAN

1;
__END__

=head1 NAME

AI::LibNeural - Perl extension libneural

=head1 SYNOPSIS

  use AI::LibNeural;

  my $nn = AI::LibNeural->new( 2, 4, 1 );

  # teach it the logical AND
  $nn->train( [ 0, 0 ], [ 0.05 ], 0.0000000005, 0.2 );
  $nn->train( [ 0, 1 ], [ 0.05 ], 0.0000000005, 0.2 );
  $nn->train( [ 1, 0 ], [ 0.05 ], 0.0000000005, 0.2 );
  $nn->train( [ 1, 1 ], [ 0.95 ], 0.0000000005, 0.2 );

  my $result = $nn->run( [ 1, 1 ] );
  # result should be ~ 0.95
  $result = $nn->run( [ 0, 1 ] );
  # result should be ~ 0.05

  $nn->save('and.mem');

=head1 ABSTRACT

  Perl bindings for the libneural c++ neural netowrk library.

=head1 DESCRIPTION

Provides accessors for the libneural library as a perl object. libneural is a
C++ library that impelements a feed-forward back-proprogation neural network.
The interface is extremely simple and should take no more than a few minutes to
master given a reasonable knowledge of back proprogation neural networks.

=head2 FUNCTIONS

=over

=item $nn = AI:LibNeural->new()

Creates an empty AI::LibNeural object, should only be used when the load method
will be called soon after.

=item $nn = AI::LibNeural->new(FILENAME)

Creates a new AI::LibNeural object from the supplied memory file.

=item $nn = AI::LibNeural->new(INTPUTS,HIDDENS,OUTPUTS)

Creates a new AI::LibNeural object with INPUTS input nodes, HIDDENS hidden
nodes, and OUTPUTS output nodes.

=item $nn->train([I1,I2,...],[O1,O2,...],MINERR,TRAINRATE)

Completes a training cycle for the given inputs I1-IN, with the expected
results of O1-OM, where N is the number of inputs and M is the number of
outputs. MINERR is the mean squared error at the output that you wish to be achieved. TRAINRATE is the learning rate to be used.

=item (O1,O2) = $nn->run([I1,I2,...])

Calculate the corresponding outputs (O1-OM) for the given inputs (I1-ON) based
on the previous training. Should only be called after the network has been
suitably trained.

=item NUM = $nn->get_layersize(WHICH)

Retrieves the number of nodes at the specified layer, WHICH. WHICH should be
one of ALL, INPUT, HIDDEN, OUTPUT. Usefully mainly with a network is loaded
from a file.

=item status = $nn->load(FILENAME)

=item status = $nn->save(FILENAME)

Loads and saves respectively the 'memory,' node configuration and weights,
of the network.  FILENAME should be the location of the file in which the
memory is stored/retrieved.

=back

=head2 EXPORT

None by default

=head2 EXPORT TAGS

=over

=item all

=over

=item ALL

  The total number of nodes on all three layers

=item INPUT

  The number of nodes on the input layer

=item HIDDEN

  The number of nodes on the hidden layer

=item OUTPUT

  The number of nodes on the output layer

=back

=back

=head1 AUTHOR

Ross McFarland E<lt>rmcfarla at neces dot comE<gt>

=head1 SEE ALSO